Instructions to use trollek/Mistral-7B-Danoia with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trollek/Mistral-7B-Danoia with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="trollek/Mistral-7B-Danoia")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("trollek/Mistral-7B-Danoia")
model = AutoModelForCausalLM.from_pretrained("trollek/Mistral-7B-Danoia", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use trollek/Mistral-7B-Danoia with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "trollek/Mistral-7B-Danoia"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trollek/Mistral-7B-Danoia",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/trollek/Mistral-7B-Danoia

SGLang

How to use trollek/Mistral-7B-Danoia with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "trollek/Mistral-7B-Danoia" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trollek/Mistral-7B-Danoia",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "trollek/Mistral-7B-Danoia" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trollek/Mistral-7B-Danoia",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use trollek/Mistral-7B-Danoia with Docker Model Runner:
```
docker model run hf.co/trollek/Mistral-7B-Danoia
```

Mistral 7B Danoia

En fintunet version af den populære franske Mistral 7B v0.3 Instruct model, specifikt tilpasset dansk med mit Danoia (CC BY 4.0) dataset.

Begrænsninger: Selvom denne model er fintunet med danske data, kan den stadig have begrænsninger i forhold til andre sprog eller domæner, og prætræningen, og kvaliteten af mit dataset... og nok mange andre ting. Det er vigtigt at teste og evaluere modellen på specifikke opgaver og data før den for alvor tages i brug.

Licens: Apache 2.0